初始化项目，由ModelHub XC社区提供模型

Model: Ba2han/test_CPTlsft2
Source: Original Platform

last-checkpoint/chat_template.jinja

@@ -0,0 +1,5 @@
+{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '
+'}}{% endif %}{% endfor %}
+{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant
+' }}{% endif %}

last-checkpoint/config.json

@@ -0,0 +1,77 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 60800,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1792,
+  "initializer_range": 0.02,
+  "intermediate_size": 4608,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 16384,
+  "max_window_layers": 40,
+  "model_name": "Ba2han/test_CPTl",
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-08,
+  "rope_parameters": {
+    "rope_theta": 500000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.14.1",
+  "unsloth_version": "2026.8.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 60802
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": [
+    60800
+  ],
+  "max_length": 16384,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.14.1",
+  "use_cache": false
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e915bcd508ef407122a9a6ad8b414d43fc7ffc93f6dc1f950f362d775bdc99
+size 2934397032

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d1d7bcb98a1df26dfdc96cbf68747c6337981f736a4a633e4259084afd82ac
+size 3631584265

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de537433b473b3b75a3c1b10ca47a1821fdf2b7b6f501ee03adc5caf6563bdf
+size 14917

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce221981a704f30cfbc27253a165c15733b7002f28ea175255b5730b028be19a
+size 14917

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64cd1f2a49ec4ae9888133233ab02ad68b5ea5b5dd47a41fc611c429196ce82a
+size 1465

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4128a9bf8a881e122f40e201d009f99eacfeb8d516d675e79fa1fd3a80beb0d1
+size 5777